Unconfined compressive strength prediction of recycled cement-treated base mixes using soft computing techniques

Abstract

ABSTRACT The study evaluates the viability of using Full-depth reclamation (FDR) as an eco-friendly approach for constructing roads. The research employs chemical stabilizers in reclaimed asphalt pavement (RAP) material to create a cement-treated base (CTB) layer. The study uses artificial neural network (ANN) models to predict the 7-days unconfined compressive strength (UCS) of RAP material-based CTB mixes. The Levenberg-Marquardt backpropagation-based ANN (LM-BP-ANN) and Scaled Conjugate Gradient backpropagation-based ANN (SCG-BP-ANN) models are used to forecast the UCS values. The models are assessed based on regression coefficient (R) and mean squared error (MSE), and the LM-BP-ANN model outperforms the SCG-BP-ANN model with an R value of 0.99556 and MSE of 0.0305. The findings suggest that the proposed models have the potential to forecast UCS values of recycled cement-treated base mixes.